CN112954707B - Energy saving method and device for base station, base station and computer readable storage medium - Google Patents

Energy saving method and device for base station, base station and computer readable storage medium Download PDF

Info

Publication number
CN112954707B
CN112954707B CN201911262430.XA CN201911262430A CN112954707B CN 112954707 B CN112954707 B CN 112954707B CN 201911262430 A CN201911262430 A CN 201911262430A CN 112954707 B CN112954707 B CN 112954707B
Authority
CN
China
Prior art keywords
base station
energy
saving
service
predicted
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201911262430.XA
Other languages
Chinese (zh)
Other versions
CN112954707A (en
Inventor
李力卡
王敏
张慧嫦
赖琮霖
张青
马泽雄
许盛宏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Telecom Corp Ltd
Original Assignee
China Telecom Corp Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Telecom Corp Ltd filed Critical China Telecom Corp Ltd
Priority to CN201911262430.XA priority Critical patent/CN112954707B/en
Publication of CN112954707A publication Critical patent/CN112954707A/en
Application granted granted Critical
Publication of CN112954707B publication Critical patent/CN112954707B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/22—Traffic simulation tools or models
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
    • H04W28/26—Resource reservation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
    • H04W52/02—Power saving arrangements
    • H04W52/0203—Power saving arrangements in the radio access network or backbone network of wireless communication networks
    • H04W52/0206—Power saving arrangements in the radio access network or backbone network of wireless communication networks in access points, e.g. base stations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/50—Allocation or scheduling criteria for wireless resources
    • H04W72/52—Allocation or scheduling criteria for wireless resources based on load
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W88/00—Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
    • H04W88/08—Access point devices
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The disclosure relates to a base station energy saving method, a base station energy saving device, a base station and a computer readable storage medium, and relates to the technical field of wireless communication. The method comprises the following steps: predicting a first predicted service load of the energy-saving base station and a first predicted service load of each adjacent base station by using a machine learning model according to current service data of the energy-saving base station and each adjacent base station thereof, and determining whether the adjacent base station with increased service load exists; under the condition that an adjacent base station with increased service load exists, predicting a second predicted service load of the energy-saving base station according to a first predicted service load of the adjacent base station and historical service load change information between the energy-saving base station and the adjacent base station; determining a predicted service load peak value of the energy-saving base station according to a first predicted service load and a second predicted service load of the energy-saving base station; and determining reserved resources of the energy-saving base station to be awakened according to the predicted service load peak value and the current resources of the energy-saving base station.

Description

Energy saving method and device for base station, base station and computer readable storage medium
Technical Field
The present disclosure relates to the field of wireless communication technologies, and in particular, to an energy saving method for a base station, an energy saving device for a base station, and a computer-readable storage medium.
Background
In the early days of the 5G era, 4G and 5G base stations were present for a long time. The user distribution of 5G is thin, and the energy consumption of the 5G base station is 3 to 4 times of that of 4G. Therefore, in order to greatly reduce the energy consumption of the base station, it is necessary to turn off part of the resources (channel) of the base station to reduce the energy consumption. Even deep high-efficiency energy-saving modes such as AAU (Active Antenna Unit) sleep, power-off of a small station and the like are adopted.
In the related art, after the base station enters these deep power saving modes, the base station automatically wakes up the device to exit the power saving mode, generally by presetting a traffic load threshold and a start-stop time range.
Disclosure of Invention
The inventors of the present disclosure found that the following problems exist in the related art described above: the limitation is large, the service recovery is not timely enough, and the method cannot be applied to different service conditions, so that the network performance is reduced.
In view of this, the present disclosure provides an energy saving technical scheme for a base station, which is applicable to timely wake up different services, so as to improve network performance under the condition of energy saving.
According to some embodiments of the present disclosure, there is provided a method of saving power of a base station, including: predicting a first predicted service load of the energy-saving base station and a first predicted service load of each adjacent base station by using a machine learning model according to current service data of the energy-saving base station and each adjacent base station thereof, and determining whether the adjacent base station with increased service load exists; under the condition that an adjacent base station with increased service load exists, predicting a second predicted service load of the energy-saving base station according to a first predicted service load of the adjacent base station and historical service load change information between the energy-saving base station and the adjacent base station; determining a predicted service load peak value of the energy-saving base station according to a first predicted service load and a second predicted service load of the energy-saving base station; and determining reserved resources of the energy-saving base station to be awakened according to the predicted service load peak value and the current resources of the energy-saving base station.
In some embodiments, the historical traffic load change information is determined based on historical traffic data between the energy efficient base station and each neighboring base station.
In some embodiments, the historical traffic load change information is determined by: acquiring historical service data between the energy-saving base station and each adjacent base station; determining a service propagation relation between the energy-saving base station and each adjacent base station according to historical service data, wherein the service propagation relation comprises service load valley points and peak points of services between the energy-saving base station and each adjacent base station in different time periods; and determining historical service load change information according to the service propagation relation.
In some embodiments, the method further comprises: predicting a predicted user experience index of the energy-saving base station and a predicted user experience index of each adjacent base station by using a machine learning model according to the current user experience indexes of the energy-saving base station and each adjacent base station; and judging whether the user experience is reduced or not according to the current user experience indexes of the energy-saving base station and each adjacent base station thereof and the predicted user experience indexes of the energy-saving base station and each adjacent base station thereof.
In some embodiments, predicting the second predicted traffic load of the energy saving base station comprises: and under the condition that the user experience is reduced, predicting a second predicted service load of the energy-saving base station.
In some embodiments, the historical traffic load change information includes traffic time information, propagation direction information, source base station traffic peak, destination base station traffic peak.
In some embodiments, the traffic time information comprises traffic propagation delay information, the traffic propagation delay information being determined from a time difference between a traffic load trough point of the energy saving base station and a traffic load trough point of the respective neighboring base station.
In some embodiments, determining the predicted traffic load peak value of the energy saving base station based on the first predicted traffic load and the second predicted traffic load of the energy saving base station comprises: determining the maximum value of the service load peak value in the first predicted service load of the energy-saving base station and the service load peak value in the second predicted service load of the energy-saving base station as the predicted service load peak value of the energy-saving base station
In some embodiments, the historical service load change information includes historical priority guarantee service volume, the priority guarantee service volume is service volume requiring low delay and high reliability, the prediction of the service load peak value includes prediction of the priority guarantee service volume, and the awakened reserved resource is preferentially used for prediction of the priority guarantee service volume.
In some embodiments, each neighboring base station is determined according to a TA (Time Advanced) in a measurement report of the energy saving base station.
According to other embodiments of the present disclosure, there is provided an energy saving apparatus of a base station, including: the first prediction unit is used for predicting a first prediction service load of the energy-saving base station and a first prediction service load of each adjacent base station by using a machine learning model according to the current service data of the energy-saving base station and each adjacent base station thereof, and is used for determining whether the adjacent base station with increased service load exists; a second prediction unit, configured to, in the presence of an adjacent base station with an increased traffic load, predict a second predicted traffic load of the energy-saving base station according to the first predicted traffic load of the adjacent base station and historical traffic load change information between the energy-saving base station and the adjacent base station; the determining unit is used for determining a predicted service load peak value of the energy-saving base station according to the first predicted service load and the second predicted service load of the energy-saving base station; and the awakening unit is used for determining reserved resources of the energy-saving base station to be awakened according to the predicted service load peak value and the current resources of the energy-saving base station.
In some embodiments, the historical traffic load change information is determined based on historical traffic data between the energy efficient base station and each neighboring base station.
In some embodiments, the historical traffic load change information is determined by: acquiring historical service data between the energy-saving base station and each adjacent base station; determining a service propagation relation between the energy-saving base station and each adjacent base station according to historical service data, wherein the service propagation relation comprises service load valley points and peak points of services between the energy-saving base station and each adjacent base station in different time periods; and determining historical service load change information according to the service propagation relation.
In some embodiments, the first prediction unit predicts the predicted user experience index of the energy-saving base station and the predicted user experience index of each adjacent base station by using a machine learning model according to the current user experience index of the energy-saving base station and each adjacent base station thereof, and judges whether the user experience is reduced according to the current user experience index of the energy-saving base station and each adjacent base station thereof and the predicted user experience index of the energy-saving base station and each adjacent base station thereof; and the second prediction unit predicts a second predicted service load of the energy-saving base station under the condition that the user experience is reduced.
In some embodiments, the historical traffic load change information includes traffic time information, propagation direction information, source base station traffic peak, destination base station traffic peak.
In some embodiments, the traffic time information comprises traffic propagation delay information, the traffic propagation delay information being determined from a time difference between a traffic load trough point of the energy saving base station and a traffic load trough point of the respective neighboring base station.
In some embodiments, the determining unit determines a maximum value of a traffic load peak value in the first predicted traffic load of the energy saving base station and a traffic load peak value in the second predicted traffic load of the energy saving base station as the predicted traffic load peak value of the energy saving base station
In some embodiments, the historical service load change information includes historical priority guarantee service volume, the priority guarantee service volume is service volume requiring low delay and high reliability, the prediction of the service load peak value includes prediction of the priority guarantee service volume, and the awakened reserved resource is preferentially used for prediction of the priority guarantee service volume.
In some embodiments, each neighboring base station is determined from the TA in the measurement report of the energy saving base station.
According to still other embodiments of the present disclosure, there is provided an energy saving apparatus of a base station, including: a memory; and a processor coupled to the memory, the processor configured to perform the method of power saving of a base station of any of the above embodiments based on instructions stored in the memory device.
According to still further embodiments of the present disclosure, there is provided a base station including: an energy saving device for the energy saving method of the base station in any of the above embodiments.
According to still further embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the power saving method of the base station in any of the above embodiments.
In the above embodiment, the predicted load peak of the base station is determined by combining two prediction results according to the current service data and the historical service data of the base station, so as to determine the reserved resource that needs to be awakened. Therefore, the method and the device can be suitable for timely awakening of different services, and therefore network performance is improved under the condition of energy conservation.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure can be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:
fig. 1 shows a flow diagram of some embodiments of a method of power saving for a base station of the present disclosure;
fig. 2 shows a schematic diagram of some embodiments of an energy saving device of a base station of the present disclosure;
fig. 3 shows a schematic diagram of some embodiments of a method of power saving of a base station of the present disclosure;
fig. 4 shows a block diagram of some embodiments of an energy saving device of a base station of the present disclosure;
fig. 5 shows a block diagram of further embodiments of an energy saving arrangement of a base station of the present disclosure;
fig. 6 shows a block diagram of further embodiments of an energy saving device of a base station of the present disclosure;
fig. 7 illustrates a block diagram of some embodiments of a base station of the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of parts and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Aiming at the technical problem, the energy-saving base station awakening method based on customer perception prediction is established in the disclosure; a large-area service propagation model is realized by adopting a manual prediction model such as area service perception; the base station energy-saving mode is responded in advance, and the resources are dynamically adjusted as required, so that the requirement of early awakening of different base stations at different time and in different service states is met; the balance between the maximum guarantee of the operation and maintenance indexes and the maximum energy-saving effect is realized.
In some embodiments, the service/high-security service propagation relationship model between the base stations is established by collecting KPIs (Key Performance Indicators) of the base stations, MR (Measurement Report), service data, base station information, and other data. Establishing an inter-base station service prediction model based on artificial intelligence; predicting the service condition of the next period of the energy-saving base station according to the service condition of the adjacent stations around the energy-saving base station; the energy-saving strategy of the base station is dynamically adjusted as required in advance; partial resource recovery or exit of power saving mode may be supported so that customer perception is not affected. For example, it can be realized by the following embodiments.
Fig. 1 shows a flow chart of some embodiments of a method of power saving of a base station of the present disclosure.
As shown in fig. 1, the method includes: step 110, determining a first predicted traffic load; step 120, determining a second predicted traffic load; step 130, determining a predicted traffic load peak value; and step 140, determining the resources that need to be woken up.
In step 110, a first predicted traffic load of the energy-saving base station and a first predicted traffic load of each neighboring base station are predicted by using a machine learning model according to current traffic data of the energy-saving base station and each neighboring base station. And determining whether the adjacent base station with increased service load exists according to the first predicted service load of each adjacent base station.
For example, the current service data may include core network signaling or DPI (Deep Packet Inspection), and the like.
For example, each neighboring base station is determined according to TA in the MR of the energy-saving base station. The adjacent base stations may be base stations within a certain distance range near the energy-saving base station, and may include peripheral base stations, peripheral base stations and the like.
For example, the Machine learning model may be a LSTM (Long Short-Term Memory), random forest, Light GBM (Light Gradient Boosting Machine), or other timing intelligent prediction model.
In step 120, in the presence of a neighboring base station with an increased traffic load, a second predicted traffic load of the energy-saving base station is predicted according to a first predicted traffic load of the neighboring base station and historical traffic load change information between the energy-saving base station and the neighboring base station.
In some embodiments, the historical traffic load change information is determined based on historical traffic data between the energy efficient base station and each neighboring base station. For example, the historical traffic data may include core network signaling or DPI, etc.
For example, the historical traffic load change information is determined by the following steps: acquiring historical service data between the energy-saving base station and each adjacent base station; and determining the service propagation relation between the energy-saving base station and each adjacent base station according to the historical service data. The service propagation relation comprises service load low-valley points and peak points of the services between the energy-saving base station and each adjacent base station in different time periods; and determining historical service load change information according to the service propagation relation.
In some embodiments, a service propagation relationship model and a priority guarantee service propagation relationship model may be respectively established according to the service load information and the priority guarantee service index. For example, the service propagation relation model comprises the valley power and peak point of the service index of the base station in different periods.
For example, the traffic load information may include RRC (Radio Resource Control), PRB (Physical Resource Block), traffic, and the like; the priority guarantee service index may include a Voice over Long-Term Evolution (VOLTE) service, a slice service volume, and the like of the cell.
In some embodiments, the historical traffic load change information includes traffic time information, propagation direction information, source base station traffic peak, destination base station traffic peak. For example, the service time information includes service propagation delay information. And the service propagation delay information is determined according to the time difference between the service load valley point of the energy-saving base station and the service load valley point of the corresponding adjacent base station.
For example, the historical traffic load change information includes time information, a traffic source base station, a traffic destination base station, propagation delay, a traffic peak value of the source base station, a traffic peak value of the destination base station, high guarantee traffic, and the like.
In some embodiments, the historical traffic load change information comprises historical priority provisioning traffic. The service volume is preferentially guaranteed to be the service volume requiring low time delay and high reliability. Predicting the peak value of the service load comprises predicting the priority guarantee service volume, wherein the awakened reserved resource is preferentially used for predicting the priority guarantee service volume.
In some embodiments, the predicted user experience index of the energy-saving base station and the predicted user experience index of each neighboring base station are predicted by using a machine learning model according to the current user experience index of the energy-saving base station and each neighboring base station. And judging whether the user experience is reduced or not according to the current user experience indexes of the energy-saving base station and each adjacent base station thereof and the predicted user experience indexes of the energy-saving base station and each adjacent base station thereof. And under the condition that the user experience is reduced, predicting a second predicted service load of the energy-saving base station.
In step 130, a predicted traffic load peak of the energy-saving base station is determined according to the first predicted traffic load and the second predicted traffic load of the energy-saving base station.
In some embodiments, the maximum of the traffic load peak in the first predicted traffic load of the energy saving base station and the traffic load peak in the second predicted traffic load of the energy saving base station is determined as the predicted traffic load peak of the energy saving base station.
In step 140, the reserved resource of the energy-saving base station to be woken up is determined according to the predicted traffic load peak value and the current resource of the energy-saving base station.
In the above embodiment, the predicted load peak of the base station is determined by combining two prediction results according to the current service data and the historical service data of the base station, so as to determine the reserved resource that needs to be awakened. Therefore, the method and the device can be suitable for timely awakening of different services, and therefore network performance is improved under the condition of energy conservation.
Fig. 2 shows a schematic diagram of some embodiments of an energy saving device of a base station of the present disclosure.
As shown in fig. 2, the energy saving device includes a network data acquisition module, an energy saving analysis engine, a base station energy saving control module, and a database. The energy-saving analysis engine comprises a data ETL (Extract-Transform-Load) module, a base station service propagation relation analysis and prediction model, a base station monitoring analysis module and the like.
In some embodiments, the network data collection module includes collection of network area plate data. For example, the network area board data collection includes collecting customer perception data (user experience index) related to the energy-saving base station, the neighbor base stations thereof, and the core network. The collected data includes KPI (including service load indicators, such as PRB, RRC user connection, service traffic; customer perception indicators, such as call drop rate, call completing rate, data service download rate, etc.), VOLTE, 5G service slice service, MR, user data, base station information, etc.
In some embodiments, big data analysis is performed according to historical data, and the rule of service propagation existing among base stations is determined, so that a base station service propagation relation analysis model is established; based on historical data of energy-saving base stations and blocks of adjacent base stations, service propagation between adjacent base stations around the energy-saving base stations and propagation of priority guarantee service are analyzed and predicted through a machine learning model, and therefore an artificial intelligent prediction model for service propagation between the base stations is established: .
In some embodiments, the data ETL module is used for pre-processing of data, such as data cleansing, denoising, uniform format, and the like.
In some embodiments, the base station monitoring and analyzing module monitors the load of the adjacent base stations of the energy-saving base station and the change condition of the customer perception index of the high-security service (priority security service); and analyzing the residual service load resources and the carrying capacity of the high-guarantee service of the energy-saving base station.
In some embodiments, the base station energy saving control module sends a new adjustment policy or instruction to the base station according to the base station monitoring analysis condition. For example, adjusting the policy or instruction includes the base station exiting the power saving mode, or partially recovering the resources.
Fig. 3 shows a schematic diagram of some embodiments of a power saving method of a base station of the present disclosure.
As shown in fig. 3, the method includes an offline portion and an online portion.
In some embodiments, the offline part comprises performing big data analysis on the traffic load propagation correlation characteristics between the base stations through historical data offline, and outputting the traffic propagation relationship between the base stations. For example, the base station is the base station a, and the offline portion includes the following steps.
In the data collection step, KPIs, MRs, traffic data (such as core network signaling or DPI data) are collected for a historical period of time (such as a month, etc.). The neighbor relation of the whole network can be calculated according to the TA of the historical MR data, for example, the neighbor of the base station A can comprise the base station B, the base station C and the like.
In the big data analysis step, modeling and calculation can be performed. For example, some service load, low latency high guarantee service (priority guarantee service) indicators may be selected, such as RRC, PRB, traffic, VOLTE of cell, slice traffic, and the like.
In some embodiments, an inter-base station traffic load propagation relationship analysis model and a high-assurance traffic propagation relationship analysis model may be established based on the selected data. For example, the rising inflection point (valley value), the peak inflection point (peak value), and the like of the traffic indicator of the base station at different time periods (such as early, middle, and late) can be measured based on big data analysis.
In the step of predicting the rule data by the base station, the traffic propagation relationship between the base stations can be calculated. For example, the traffic propagation relationship includes a traffic-related time period, a propagation direction (e.g., propagation from base station B to base station a), and a propagation time difference (e.g., a rising inflection point of base station B, a peak inflection point time offset from a rising inflection point of base station a, and a peak inflection point de time offset). The traffic propagation relationship may further include a common traffic load variation, an average value of high-guarantee traffic variations, and the like.
In some embodiments, the service propagation relation database and the high-security service propagation relation database, that is, historical service load change information, may be output respectively according to the establishment of the service load propagation relation analysis model and the high-security service propagation relation analysis model between the base stations.
In some embodiments, the line part comprises predicting traffic propagation conditions on the line according to the traffic data of the adjacent stations around the energy-saving base station.
And the base station enters an energy-saving turn-off state, such as channel turn-off, power-off of the base station and the like. And carrying out data acquisition on the energy-saving base station. For example, near real-time data acquisition may be performed online (e.g., within 1 hour). The collected data can report KPI (including customer perception data) data, high-security service condition (core network signaling or DPI data) and the like.
In the step of monitoring customer perception and service data, the data of peripheral stations which are adjacent to the energy-saving base station A and are even farther away are monitored aiming at the energy-saving base station A.
In the step of predicting the service data in the artificial intelligence manner, service loads, customer perception indexes and the like of adjacent stations (which may include more peripheral adjacent stations) and the energy-saving base station A in the next period are predicted based on historical data of the latest period through a time-series intelligent prediction model (such as LSTM, random forest, lightGBM and the like).
In some embodiments, it may be determined whether there is a traffic rise change based on the prediction of the neighboring base station. And if so, calculating the traffic lifting condition of the base station A in the next period by combining the service propagation relation database. For example, the traffic rise condition includes a time point, a traffic peak, a high-guarantee service condition, and the like. The larger of the traffic peak result and the predicted peak value of the base station a in the next period can be output.
In some embodiments, the base station energy saving mode may be adjusted. For example, according to the service prediction situation (service peak, whether there is high-security service) of the next period of the energy-saving base station, the energy-saving mode adjustment of the base station is completed in advance.
In the step of judging whether the residual resources can bear the newly added load, whether the current configuration of the base station A can meet the predicted resource requirement of the service is evaluated.
Under the condition that the working resources of the base station A cannot meet the predicted resource requirements during energy-saving shutdown, initiating an energy-saving strategy adjustment instruction for the energy-saving base station A in advance; and under the condition that the resources of the base station A which can be turned off in an energy-saving mode and work can meet the demand of the predicted resources, the steps of monitoring the customer perception and the service data are repeated.
In the step of determining whether the remaining resources can partially satisfy the load, the energy saving policy adjusting instruction may include: awakening part of resources such as part of transceiving units and relay resources as required; exit the energy saving mode, etc. For example, if the condition cannot be met, the base station a exits the energy saving state and wakes up all resources; if so, awakening the corresponding partial resource.
In some embodiments, assume that energy-saving base station a has turned on channel off or deep sleep, its neighbor has base station B, C, etc. There may be a situation where traffic from base station B enters base station a and then goes to other neighboring base stations.
In this case, whether there is a propagation relationship and rule of traffic from the base station B to the base station a can be measured offline in advance through big data.
In some embodiments, through historical big data analysis, the rising edge and peak structure of the traffic between the adjacent base stations can be determined, so as to determine the traffic propagation correlation law of a certain period (such as 6-7 points) which repeatedly occurs between the two. According to the rule, a base station service propagation rule data table can be established.
In some embodiments, the base station traffic propagation law data table may include a recording time, a source base station, a destination base station, an average propagation delay (e.g., minutes), a certain load index peak of the source base station, a certain load index peak 2 of the destination base station, and a high guaranteed traffic volume. For example, one piece of data in the base station traffic propagation law data table may include (6:00, base station B, base station a, 30, 50, 55, 10).
In some embodiments, online analytical predictions may be made. For example, the following steps may be included.
And monitoring the service and customer perception data of peripheral stations and even farther peripheral stations aiming at the energy-saving base station A.
And predicting the traffic load and customer perception index data of the adjacent station B and the energy-saving base station A in the next period based on the historical data of the latest period by using a time sequence intelligent prediction model (such as LSTM, random forest, lightGBM and the like). Such as PRB, RRC, high-assurance traffic, etc.
And based on the prediction result of the adjacent base station B, if the traffic volume is changed in an ascending way, the traffic volume change condition of the base station A in the next period is calculated by combining the base station traffic propagation rule data table.
In some embodiments, it may be determined whether the traffic of the base station a is increased according to the traffic variation of the next cycle. And judging whether the predicted service peak value is a high-guarantee service or not. For example, the traffic result and the predicted value of the next cycle of the base station a may be output with the maximum value. And awakening the corresponding resource of the base station A under the condition that the predicted service peak value is judged to be the high-security service so as to ensure the execution of the high-security service.
In some embodiments, the base station energy saving mode may be adjusted based on the prediction. The energy-saving mode adjustment of the base station can be completed in advance according to the service prediction condition (service peak value, whether high-guarantee service exists or not) of the next period of the energy-saving base station.
For example, it may be evaluated whether the current configuration of base station a can meet the predicted resource requirements of the service; if the resources of the base station A which is in energy-saving shutdown and works cannot meet the predicted resource requirements, an energy-saving strategy adjusting instruction for the energy-saving base station A can be initiated in advance.
For example, the energy saving policy adjustment instruction may include: if the resource is sufficient, no wake-up is required; if the resources are partially insufficient, wake up the base station A partial resources, e.g., from 16T16R to 32T 32R; if the resources are seriously insufficient, the base station A exits the energy-saving mode.
In the above embodiments, the energy saving base station may be adjusted based on artificial intelligence, a priori intelligent prediction. And predicting the service change trend of the energy-saving base station in advance according to the service propagation relation of the adjacent base stations, thereby realizing intelligent perception.
In the above embodiments, the intelligent control strategy can implement partial or full recovery as needed. The accurate selection can be that the base station resources are partially recovered or the energy-saving mode is completely exited according to the requirement, so that the ping-pong effect is avoided, and the maximized energy saving is realized;
in the above embodiment, the energy-efficient scheme is easier to deploy on a large scale. It is very difficult to preset the power restoration index threshold value for each base station based on experience, and the service cannot be dynamically adapted. The method can automatically and intelligently adapt and adjust, so that the efficient and energy-saving scale application of the base station is easier and feasible, the maintenance efficiency is improved, and the worries about the later use are avoided.
Fig. 4 illustrates a block diagram of some embodiments of an energy saving device of a base station of the present disclosure.
As shown in fig. 4, the energy saving device 4 of the base station includes a first prediction unit 41, a second prediction unit 42, a determination unit 43, and a wake-up unit 44.
The first prediction unit 41 predicts the first predicted traffic load of the energy-saving base station and the first predicted traffic load of each neighboring base station using a machine learning model based on the current traffic data of the energy-saving base station and its neighboring base stations. The first predicted traffic load of each neighboring base station is used to determine whether there is a neighboring base station with an increased traffic load.
In some embodiments, each neighboring base station is determined from the TA in the measurement report of the energy saving base station.
The second prediction unit 42 predicts the second predicted traffic load of the energy saving base station based on the first predicted traffic load of the adjacent base station and the historical traffic load change information between the energy saving base station and the adjacent base station in the case where there is the adjacent base station having the traffic load increased.
In some embodiments, the historical traffic load change information is determined based on historical traffic data between the energy efficient base station and each neighboring base station.
In some embodiments, the historical traffic load change information is determined by: acquiring historical service data between the energy-saving base station and each adjacent base station; determining a service propagation relation between the energy-saving base station and each adjacent base station according to historical service data, wherein the service propagation relation comprises service load valley points and peak points of services between the energy-saving base station and each adjacent base station in different time periods; and determining historical service load change information according to the service propagation relation.
In some embodiments, the historical traffic load change information includes traffic time information, propagation direction information, source base station traffic peak, destination base station traffic peak.
In some embodiments, the traffic time information comprises traffic propagation delay information, the traffic propagation delay information being determined from a time difference between a traffic load trough point of the energy saving base station and a traffic load trough point of the respective neighboring base station.
In some embodiments, the historical service load change information includes historical priority guarantee service volume, the priority guarantee service volume is service volume requiring low delay and high reliability, the prediction of the service load peak value includes prediction of the priority guarantee service volume, and the awakened reserved resource is preferentially used for prediction of the priority guarantee service volume.
In some embodiments, the first prediction unit 41 predicts the predicted user experience index of the energy-saving base station and the predicted user experience index of each neighboring base station by using a machine learning model according to the current user experience index of the energy-saving base station and each neighboring base station; judging whether the user experience is reduced or not according to the current user experience indexes of the energy-saving base station and each adjacent base station thereof and the predicted user experience indexes of the energy-saving base station and each adjacent base station thereof; the second prediction unit 42 predicts the second predicted traffic load of the energy saving base station in case of degraded user experience.
The determining unit 43 determines the predicted traffic load peak value of the energy-saving base station according to the first predicted traffic load and the second predicted traffic load of the energy-saving base station.
The awakening unit 44 determines reserved resources of the energy-saving base station to be awakened according to the predicted traffic load peak value and the current resources of the energy-saving base station.
In some embodiments, the determining unit 43 determines the maximum value of the traffic load peak value in the first predicted traffic load of the energy-saving base station and the traffic load peak value in the second predicted traffic load of the energy-saving base station as the predicted traffic load peak value of the energy-saving base station
In the above embodiment, the predicted load peak of the base station is determined by combining two prediction results according to the current service data and the historical service data of the base station, so as to determine the reserved resource that needs to be awakened. Therefore, the method and the device can be suitable for timely awakening of different services, and therefore network performance is improved under the condition of energy conservation.
Fig. 5 shows a block diagram of further embodiments of an energy saving arrangement of a base station of the present disclosure.
As shown in fig. 5, the energy saving device 5 of the base station of this embodiment includes: a memory 51 and a processor 52 coupled to the memory 51, the processor 52 being configured to execute a method of saving power of a base station in any of the embodiments of the present disclosure based on instructions stored in the memory 51.
The memory 51 may include, for example, a system memory, a fixed nonvolatile storage medium, and the like. The system memory stores, for example, an operating system, application programs, a boot loader, a database, and other programs.
Fig. 6 shows a block diagram of further embodiments of the power saving device of the base station of the present disclosure.
As shown in fig. 6, the energy saving device 6 of the base station of this embodiment includes: a memory 610 and a processor 620 coupled to the memory 610, the processor 620 being configured to perform the method of saving power of a base station in any of the foregoing embodiments based on instructions stored in the memory 610.
The memory 610 may include, for example, system memory, fixed non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a boot loader, and other programs.
The power saving device 6 of the base station may further include an input output interface 630, a network interface 640, a storage interface 650, and the like. These interfaces 630, 640, 650 and the connections between the memory 610 and the processor 620 may be through a bus 660, for example. The input/output interface 630 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 640 provides a connection interface for various networking devices. The storage interface 650 provides a connection interface for external storage devices such as an SD card and a usb disk.
Fig. 7 illustrates a block diagram of some embodiments of a base station of the present disclosure.
As shown in fig. 7, the base station 7 comprises an energy saving means 71 for the energy saving method of the base station in any of the above embodiments.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media having computer-usable program code embodied therein.
So far, the power saving method of the base station, the power saving apparatus of the base station, and the computer readable storage medium according to the present disclosure have been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
The method and system of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the foregoing examples are for purposes of illustration only and are not intended to limit the scope of the present disclosure. It will be appreciated by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims (21)

1. A method of saving power in a base station, comprising:
predicting a first predicted service load of the energy-saving base station and a first predicted service load of each adjacent base station by using a machine learning model according to current service data of the energy-saving base station and each adjacent base station, wherein the first predicted service loads of the energy-saving base station and each adjacent base station are used for determining whether the adjacent base station with increased service load exists;
under the condition that an adjacent base station with increased service load exists, predicting a second predicted service load of the energy-saving base station according to a first predicted service load of the adjacent base station and historical service load change information between the energy-saving base station and the adjacent base station;
determining a predicted service load peak value of the energy-saving base station according to a first predicted service load and a second predicted service load of the energy-saving base station;
and determining reserved resources of the energy-saving base station which needs to be awakened according to the predicted service load peak value and the current resources of the energy-saving base station.
2. The energy saving method according to claim 1,
and the historical service load change information is determined according to historical service data between the energy-saving base station and each adjacent base station.
3. The energy saving method according to claim 2,
the historical traffic load change information is determined by the following steps:
acquiring historical service data between the energy-saving base station and each adjacent base station;
determining a service propagation relationship between the energy-saving base station and each adjacent base station according to the historical service data, wherein the service propagation relationship comprises service load low-valley points and peak points of services between the energy-saving base station and each adjacent base station in different time periods;
and determining the historical service load change information according to the service propagation relation.
4. The energy saving method of claim 1, further comprising:
predicting a predicted user experience index of the energy-saving base station and a predicted user experience index of each adjacent base station by using the machine learning model according to the current user experience indexes of the energy-saving base station and each adjacent base station;
judging whether the user experience is reduced or not according to the current user experience indexes of the energy-saving base station and each adjacent base station thereof and the predicted user experience indexes of the energy-saving base station and each adjacent base station thereof;
wherein the predicting a second predicted traffic load of the energy saving base station comprises:
and under the condition that the user experience is reduced, predicting a second predicted service load of the energy-saving base station.
5. The energy saving method according to claim 1,
the historical service load change information comprises service time information, propagation direction information, a source base station service volume peak value and a target base station service volume peak value.
6. The energy saving method according to claim 5,
the service time information includes service propagation delay information,
and the service propagation delay information is determined according to the time difference between the service load valley point of the energy-saving base station and the service load valley point of the corresponding adjacent base station.
7. The energy saving method according to any one of claims 1 to 6, wherein the determining the predicted traffic load peak value of the energy saving base station according to the first predicted traffic load and the second predicted traffic load of the energy saving base station comprises:
and determining the maximum value of the service load peak value in the first predicted service load of the energy-saving base station and the service load peak value in the second predicted service load of the energy-saving base station as the predicted service load peak value of the energy-saving base station.
8. The energy saving method according to any one of claims 1 to 6,
the historical service load change information comprises historical priority guarantee service volume which is service volume requiring low time delay and high reliability,
the predicting of the peak value of the service load comprises predicting of a priority guarantee service volume, and awakened reserved resources are preferentially used for predicting the priority guarantee service volume.
9. The energy saving method according to any one of claims 1 to 6,
and each adjacent base station is determined according to the TA in the measurement report of the energy-saving base station.
10. An energy saving apparatus of a base station, comprising:
the first prediction unit is used for predicting a first prediction service load of the energy-saving base station and the first prediction service load of each adjacent base station by using a machine learning model according to the current service data of the energy-saving base station and each adjacent base station thereof, and is used for determining whether the adjacent base station with increased service load exists;
a second prediction unit, configured to, in the presence of an adjacent base station with an increased traffic load, predict a second predicted traffic load of the energy-saving base station according to a first predicted traffic load of the adjacent base station and historical traffic load change information between the energy-saving base station and the adjacent base station;
a determining unit, configured to determine a predicted traffic load peak of the energy-saving base station according to a first predicted traffic load and a second predicted traffic load of the energy-saving base station;
and the awakening unit is used for determining reserved resources of the energy-saving base station to be awakened according to the predicted service load peak value and the current resources of the energy-saving base station.
11. The energy saving device of claim 10,
and the historical service load change information is determined according to historical service data between the energy-saving base station and each adjacent base station.
12. The energy saving device of claim 10,
the historical traffic load change information is determined by the following steps:
acquiring historical service data between the energy-saving base station and each adjacent base station;
determining a service propagation relation between the energy-saving base station and each adjacent base station according to the historical service data, wherein the service propagation relation comprises service load low-valley points and peak points of services between the energy-saving base station and each adjacent base station in different time periods;
and determining the historical service load change information according to the service propagation relation.
13. The energy saving device of claim 10,
the first prediction unit predicts a predicted user experience index of the energy-saving base station and a predicted user experience index of each adjacent base station by using the machine learning model according to the current user experience indexes of the energy-saving base station and each adjacent base station thereof, and judges whether the user experience is reduced or not according to the current user experience indexes of the energy-saving base station and each adjacent base station thereof and the predicted user experience indexes of the energy-saving base station and each adjacent base station thereof;
and the second prediction unit predicts a second predicted service load of the energy-saving base station under the condition that the user experience is reduced.
14. The energy saving device of claim 10,
the historical service load change information comprises service time information, propagation direction information, a source base station service volume peak value and a target base station service volume peak value.
15. The energy saving device of claim 14,
the service time information includes service propagation delay information,
and the service propagation delay information is determined according to the time difference between the service load valley point of the energy-saving base station and the service load valley point of the corresponding adjacent base station.
16. The energy saving device according to any one of claims 10 to 15,
the determining unit determines a maximum value of a traffic load peak value in a first predicted traffic load of the energy-saving base station and a traffic load peak value in a second predicted traffic load of the energy-saving base station as a predicted traffic load peak value of the energy-saving base station.
17. The energy saving device according to any one of claims 10 to 15,
the historical service load change information comprises historical priority guarantee service volume which is service volume requiring low time delay and high reliability,
the predicting of the peak value of the service load comprises predicting of a priority guarantee service volume, and awakened reserved resources are preferentially used for predicting the priority guarantee service volume.
18. The energy saving device according to any one of claims 10 to 15,
and each adjacent base station is determined according to the TA in the measurement report of the energy-saving base station.
19. An energy saving device of a base station, comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the method of energy saving of a base station of any of claims 1-9 based on instructions stored in the memory.
20. A base station, comprising:
energy saving means for performing the energy saving method of the base station of any one of claims 1 to 9.
21. A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, implements the method for energy saving of a base station of any one of claims 1-9.
CN201911262430.XA 2019-12-11 2019-12-11 Energy saving method and device for base station, base station and computer readable storage medium Active CN112954707B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911262430.XA CN112954707B (en) 2019-12-11 2019-12-11 Energy saving method and device for base station, base station and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911262430.XA CN112954707B (en) 2019-12-11 2019-12-11 Energy saving method and device for base station, base station and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN112954707A CN112954707A (en) 2021-06-11
CN112954707B true CN112954707B (en) 2022-09-16

Family

ID=76225990

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911262430.XA Active CN112954707B (en) 2019-12-11 2019-12-11 Energy saving method and device for base station, base station and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN112954707B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113438687B (en) * 2021-06-23 2022-10-11 中国联合网络通信集团有限公司 Base station awakening method, device and equipment
CN116405990A (en) * 2021-12-28 2023-07-07 中兴通讯股份有限公司 Equipment energy saving method, system, electronic equipment and storage medium
CN117279033A (en) * 2022-06-15 2023-12-22 中兴通讯股份有限公司 Inter-cell interference coordination method, device and storage medium
CN117692941A (en) * 2022-08-25 2024-03-12 中兴通讯股份有限公司 Dynamic load prediction method, device, base station and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2530979A1 (en) * 2011-06-03 2012-12-05 Alcatel Lucent A base station, a network, and a method of base station switching between modes
EP2849478A1 (en) * 2013-09-13 2015-03-18 Alcatel Lucent A base station and a method of a base station estimating traffic load on a neighbouring base station
CN104883725A (en) * 2015-06-19 2015-09-02 东南大学 Method for network energy conservation based on station actual load in long-term evolution network
EP2919531A1 (en) * 2014-03-10 2015-09-16 Aspire Technology Limited Method and system for determining where and when in a cellular mobile network power consumption savings can be achieved without impacting quality of service
CN105611545A (en) * 2014-11-19 2016-05-25 中兴通讯股份有限公司 Base station interference coordination method, base station interference coordination device and base station interference coordination system
EP3122099A1 (en) * 2015-07-24 2017-01-25 Cisco Technology, Inc. System and method to facilitate radio access point load prediction in a network environment

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110102589A (en) * 2010-03-11 2011-09-19 삼성전자주식회사 Apparatus and method for reducing energy consumption in wireless communication system
EP2439988B1 (en) * 2010-10-08 2014-06-25 Alcatel Lucent Optimizing power consumption of a base station

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2530979A1 (en) * 2011-06-03 2012-12-05 Alcatel Lucent A base station, a network, and a method of base station switching between modes
EP2849478A1 (en) * 2013-09-13 2015-03-18 Alcatel Lucent A base station and a method of a base station estimating traffic load on a neighbouring base station
EP2919531A1 (en) * 2014-03-10 2015-09-16 Aspire Technology Limited Method and system for determining where and when in a cellular mobile network power consumption savings can be achieved without impacting quality of service
CN105611545A (en) * 2014-11-19 2016-05-25 中兴通讯股份有限公司 Base station interference coordination method, base station interference coordination device and base station interference coordination system
CN104883725A (en) * 2015-06-19 2015-09-02 东南大学 Method for network energy conservation based on station actual load in long-term evolution network
EP3122099A1 (en) * 2015-07-24 2017-01-25 Cisco Technology, Inc. System and method to facilitate radio access point load prediction in a network environment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
AI技术在5G基站节能应用的展望;张青;《广东通信技术》;20191015(第10期);全文 *
基于基站休眠的蜂窝网络节能技术研究;朱禹涛等;《电信网技术》;20151015(第10期);全文 *

Also Published As

Publication number Publication date
CN112954707A (en) 2021-06-11

Similar Documents

Publication Publication Date Title
CN112954707B (en) Energy saving method and device for base station, base station and computer readable storage medium
KR101529539B1 (en) Method and apparatus of smart power management for mobile communication terminals
CN104424031B (en) Method and device for controlling working frequency of processor
CN105636056B (en) Energy-saving method, device and system for optimizing spectrum resources
Tong et al. Application-aware traffic scheduling for workload offloading in mobile clouds
KR20130127508A (en) Method and apparatus of smart power management for mobile communication terminals using power thresholds
CN113543284A (en) Energy saving method, base station, control unit and storage medium
CN110996377B (en) Base station energy saving method, system, device and storage medium
WO2016078268A1 (en) Energy saving method and device
WO2016115956A1 (en) Scheduling method and scheduling device for business system based on cloud computing
CN102498735B (en) For the method and apparatus that community controls
KR20210097828A (en) Intelligent terminal energy saving method and device based on AI prediction
CN109600765B (en) Dormancy and awakening control method and device, DU (data Unit), CU (Central Unit) and storage medium
TWI572179B (en) Mobile network base station communication prediction and resource scheduling automation analysis system and method
US20130102301A1 (en) Control apparatus and method, and node apparatus
CN109756372B (en) Elastic expansion method and device for telecommunication charging system
CN111148189A (en) User terminal, control method thereof, and computer-readable storage medium
CN104699224A (en) Power-saving control method
WO2023109496A1 (en) Resource allocation method and apparatus, and server and storage medium
CN106912088B (en) A kind of control method and device of small base station dormancy
CN105700665B (en) Selection method based on power consumption of embedded system pattern and system, embedded system
CN115243349A (en) Base station energy saving method and device, electronic equipment and storage medium
CN107005935A (en) Network energy efficiency optimization method and device
CN114071662A (en) Base station and energy-saving control method and device thereof
CN108430098B (en) Wireless communication terminal and power saving method thereof

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant